Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 128 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.7107. Min Act: -0.0000

Data Index: 1451992 (The Pile)

Max Activating Token Index: 164

Text #1

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5582. Min Act: -0.0000

Data Index: 708917 (The Pile)

Max Activating Token Index: 65

Text #2

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1531937 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1154015 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1677802 (The Pile)

Max Activating Token Index: 581

Text #5

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5140. Min Act: -0.0000

Data Index: 995984 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5404. Min Act: -0.0000

Data Index: 894222 (The Pile)

Max Activating Token Index: 298

Text #7

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.5059. Min Act: -0.0000

Data Index: 265638 (The Pile)

Max Activating Token Index: 607

Text #8

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1938393 (The Pile)

Max Activating Token Index: 190

Text #9

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4517. Min Act: -0.0000

Data Index: 404400 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4281. Min Act: -0.0000

Data Index: 1371574 (The Pile)

Max Activating Token Index: 88

Text #11

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1854665 (The Pile)

Max Activating Token Index: 1010

Text #12

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4372. Min Act: -0.0000

Data Index: 191593 (The Pile)

Max Activating Token Index: 199

Text #13

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4367. Min Act: -0.0000

Data Index: 822037 (The Pile)

Max Activating Token Index: 438

Text #14

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4131. Min Act: -0.0000

Data Index: 607844 (The Pile)

Max Activating Token Index: 842

Text #15

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1965499 (The Pile)

Max Activating Token Index: 346

Text #16

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4064. Min Act: -0.0000

Data Index: 236596 (The Pile)

Max Activating Token Index: 342

Text #17

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1170166 (The Pile)

Max Activating Token Index: 849

Text #18

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.3917. Min Act: -0.0000

Data Index: 1752795 (The Pile)

Max Activating Token Index: 964

Text #19

Max Range: 0.7107. Min Range: -0.7107

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1029121 (The Pile)

Max Activating Token Index: 558